Project 02 · MCP + RAG

Product-Matching MCP over a Dual Datastore

A retrieval layer that matches 2,000+ products to each RFP's requirements — exposed to the agent through the Model Context Protocol.

Python FastMCPpgvectorReciprocal Rank FusionMongoDBHybrid search

The problem

Matching 2k+ Pitsco products to each RFP's requirements was manual and inconsistent — a bottleneck that slowed every proposal and let good-fit products slip through.

What I built

System architecture

🧩
Architecture diagram — coming soon
MCP server · hybrid retrieval (tsvector + pgvector) · RRF · Postgres + MongoDB. (Upload diagram here.)

Demo

Walkthrough video — coming soon
Show a query → hybrid match → ranked products.

Stack

PythonFastMCPpgvectorOpenAI embeddingsPostgres full-textMongoDBRRF

Outcome

~50% faster product matching Gave every agent workflow one grounded product knowledge source.

← Prev: RFP DiscoveryNext: Standards Platform →Home